MosaicFusion: diffusion models as data augmenters for large vocabulary instance segmentation

• المؤلفون الرئيسيون: Xie, Jiahao, Li, Wei, Li, Xiangtai, Liu, Ziwei, Ong, Yew Soon, Loy, Chen Change
• مؤلفون آخرون: College of Computing and Data Science
• التنسيق: مقال
• اللغة: English
• منشور في: 2025
• الموضوعات: Computer and Information Science; Text-to-image diffusion models; Long tail
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/182213
• المؤسسة: Nanyang Technological University

We present MosaicFusion, a simple yet effective diffusion-based data augmentation approach for large vocabulary instance segmentation. Our method is training-free and does not rely on any label supervision. Two key designs enable us to employ an off-the-shelf text-to-image diffusion model as a usefu...